@inproceedings{straton-etal-2020-stigma,
title = "Stigma Annotation Scheme and Stigmatized Language Detection in Health-Care Discussions on Social Media",
author = "Straton, Nadiya and
Jang, Hyeju and
Ng, Raymond",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.148",
pages = "1178--1190",
abstract = "Much research has been done within the social sciences on the interpretation and influence of stigma on human behaviour and health, which result in out-of-group exclusion, distancing, cognitive separation, status loss, discrimination, in-group pressure, and often lead to disengagement, non-adherence to treatment plan, and prescriptions by the doctor. However, little work has been conducted on computational identification of stigma in general and in social media discourse in particular. In this paper, we develop the annotation scheme and improve the annotation process for stigma identification, which can be applied to other health-care domains. The data from pro-vaccination and anti-vaccination discussion groups are annotated by trained annotators who have professional background in social science and health-care studies, therefore the group can be considered experts on the subject in comparison to non-expert crowd. Amazon MTurk annotators is another group of annotator with no knowledge on their education background, they are initially treated as non-expert crowd on the subject matter of stigma. We analyze the annotations with visualisation techniques, features from LIWC (Linguistic Inquiry and Word Count) list and make prediction based on bi-grams with traditional and deep learning models. Data augmentation method and application of CNN show high performance accuracy in comparison to other models. Success of the rigorous annotation process on identifying stigma is reconfirmed by achieving high prediction rate with CNN.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="straton-etal-2020-stigma">
<titleInfo>
<title>Stigma Annotation Scheme and Stigmatized Language Detection in Health-Care Discussions on Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nadiya</namePart>
<namePart type="family">Straton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyeju</namePart>
<namePart type="family">Jang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raymond</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Much research has been done within the social sciences on the interpretation and influence of stigma on human behaviour and health, which result in out-of-group exclusion, distancing, cognitive separation, status loss, discrimination, in-group pressure, and often lead to disengagement, non-adherence to treatment plan, and prescriptions by the doctor. However, little work has been conducted on computational identification of stigma in general and in social media discourse in particular. In this paper, we develop the annotation scheme and improve the annotation process for stigma identification, which can be applied to other health-care domains. The data from pro-vaccination and anti-vaccination discussion groups are annotated by trained annotators who have professional background in social science and health-care studies, therefore the group can be considered experts on the subject in comparison to non-expert crowd. Amazon MTurk annotators is another group of annotator with no knowledge on their education background, they are initially treated as non-expert crowd on the subject matter of stigma. We analyze the annotations with visualisation techniques, features from LIWC (Linguistic Inquiry and Word Count) list and make prediction based on bi-grams with traditional and deep learning models. Data augmentation method and application of CNN show high performance accuracy in comparison to other models. Success of the rigorous annotation process on identifying stigma is reconfirmed by achieving high prediction rate with CNN.</abstract>
<identifier type="citekey">straton-etal-2020-stigma</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.148</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>1178</start>
<end>1190</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Stigma Annotation Scheme and Stigmatized Language Detection in Health-Care Discussions on Social Media
%A Straton, Nadiya
%A Jang, Hyeju
%A Ng, Raymond
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F straton-etal-2020-stigma
%X Much research has been done within the social sciences on the interpretation and influence of stigma on human behaviour and health, which result in out-of-group exclusion, distancing, cognitive separation, status loss, discrimination, in-group pressure, and often lead to disengagement, non-adherence to treatment plan, and prescriptions by the doctor. However, little work has been conducted on computational identification of stigma in general and in social media discourse in particular. In this paper, we develop the annotation scheme and improve the annotation process for stigma identification, which can be applied to other health-care domains. The data from pro-vaccination and anti-vaccination discussion groups are annotated by trained annotators who have professional background in social science and health-care studies, therefore the group can be considered experts on the subject in comparison to non-expert crowd. Amazon MTurk annotators is another group of annotator with no knowledge on their education background, they are initially treated as non-expert crowd on the subject matter of stigma. We analyze the annotations with visualisation techniques, features from LIWC (Linguistic Inquiry and Word Count) list and make prediction based on bi-grams with traditional and deep learning models. Data augmentation method and application of CNN show high performance accuracy in comparison to other models. Success of the rigorous annotation process on identifying stigma is reconfirmed by achieving high prediction rate with CNN.
%U https://aclanthology.org/2020.lrec-1.148
%P 1178-1190
Markdown (Informal)
[Stigma Annotation Scheme and Stigmatized Language Detection in Health-Care Discussions on Social Media](https://aclanthology.org/2020.lrec-1.148) (Straton et al., LREC 2020)
ACL